diff options
| -rw-r--r-- | test/test_ted_subtitles.py | 6 | ||||
| -rw-r--r-- | youtube_dl/extractor/ted.py | 24 |
2 files changed, 22 insertions, 8 deletions
diff --git a/test/test_ted_subtitles.py b/test/test_ted_subtitles.py index 3283253ab..a0dd7eeed 100644 --- a/test/test_ted_subtitles.py +++ b/test/test_ted_subtitles.py @@ -51,6 +51,12 @@ class TestTedSubtitles(unittest.TestCase): self.DL.params['subtitleslang'] = ['en'] subtitles = self.getSubtitles() self.assertTrue(len(subtitles.keys()) == 0) + # def test_nosubtitles(self): + # self.DL.expect_warning(u'video doesn\'t have subtitles') + # self.url = 'http://www.ted.com/talks/rodrigo_canales_the_deadly_genius_of_drug_cartels.html' + # self.DL.params['writesubtitles'] = True + # self.DL.params['allsubtitles'] = True + # subtitles = self.getSubtitles() def test_multiple_langs(self): self.DL.params['writesubtitles'] = True langs = ['es', 'fr', 'de'] diff --git a/youtube_dl/extractor/ted.py b/youtube_dl/extractor/ted.py index 239e2a448..1b006bc9b 100644 --- a/youtube_dl/extractor/ted.py +++ b/youtube_dl/extractor/ted.py @@ -3,6 +3,11 @@ import re from .subtitles import SubtitlesInfoExtractor +from ..utils import ( + compat_str, + RegexNotFoundError, +) + class TEDIE(SubtitlesInfoExtractor): _VALID_URL=r'''http://www\.ted\.com/ ( @@ -105,12 +110,15 @@ class TEDIE(SubtitlesInfoExtractor): return info def _get_available_subtitles(self, video_id, webpage): - options = self._search_regex(r'(?:<select name="subtitles_language_select" id="subtitles_language_select">)(.*?)(?:</select>)', webpage, 'subtitles_language_select', flags=re.DOTALL) - languages = re.findall(r'(?:<option value=")(\S+)"', options) - if languages: - sub_lang_list = {} - for l in languages: - url = 'http://www.ted.com/talks/subtitles/id/%s/lang/%s/format/srt' % (video_id, l) - sub_lang_list[l] = url - return sub_lang_list + try: + options = self._search_regex(r'(?:<select name="subtitles_language_select" id="subtitles_language_select">)(.*?)(?:</select>)', webpage, 'subtitles_language_select', flags=re.DOTALL) + languages = re.findall(r'(?:<option value=")(\S+)"', options) + if languages: + sub_lang_list = {} + for l in languages: + url = 'http://www.ted.com/talks/subtitles/id/%s/lang/%s/format/srt' % (video_id, l) + sub_lang_list[l] = url + return sub_lang_list + except RegexNotFoundError as err: + self._downloader.report_warning(u'video doesn\'t have subtitles') return {} |